Jinzhen Lin baaa2b24da [Bugfix] fix moe_wna16 get_quant_method (#12648) ...

Fix https://github.com/vllm-project/vllm/issues/12647
The `get_quant_method` of `moe_wna16` always return moe method,
GPTQ-based linear method or AWQ-based linear method, even when the
target module is attention layer.


https://github.com/vllm-project/vllm/blob/baeded25699f9f4851843306f27f685c4d4ee7c5/vllm/attention/layer.py#L86-L92

Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>

2025-02-02 15:29:56 +08:00

..

fused_moe

Apply torch.compile to fused_moe/grouped_topk (#12637)

2025-02-01 16:16:19 +00:00

mamba

[MODEL] LoRA support for Jamba model (#11209)

2024-12-27 17:58:21 +00:00

quantization

[Bugfix] fix moe_wna16 get_quant_method (#12648)

2025-02-02 15:29:56 +08:00

__init__.py

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

activation.py

[CI/Build][CPU][Bugfix] Fix CPU CI (#12150)

2025-01-17 19:39:52 +08:00

layernorm.py

[Model] Add has_weight to RMSNorm and re-enable weights loading tracker for Mamba (#10739)

2024-12-10 10:23:07 +08:00

linear.py

[Model] Support for fairseq2 Llama (#11442)

2025-01-19 10:40:40 -08:00

logits_processor.py

Support torchrun and SPMD-style offline inference (#12071)

2025-01-16 19:58:53 +08:00

pooler.py

[Frontend] Separate pooling APIs in offline inference (#11129)

2024-12-13 10:40:07 +00:00

rejection_sampler.py

[platform] support custom torch.compile backend key (#11318)

2025-01-10 23:46:51 +08:00

resampler.py

[Model] Remove unnecessary weight initialization logic (#11736)

2025-01-04 23:46:21 +08:00

rotary_embedding.py

[V1] Add V1 support of Qwen2-VL (#12128)

2025-01-19 19:52:13 +08:00

sampler.py

Update pre-commit hooks (#12475)

2025-01-27 17:23:08 -07:00

spec_decode_base_sampler.py

Remove hard-dependencies of Speculative decode to CUDA workers (#10587)

2024-11-26 17:57:11 -08:00

typical_acceptance_sampler.py

Fix typical acceptance sampler with correct recovered token ids (#8562)

2024-09-23 12:32:27 -07:00

utils.py

[V1] Adding min tokens/repetition/presence/frequence penalties to V1 sampler (#10681)

2024-12-26 19:02:58 +09:00

vocab_parallel_embedding.py

Update pre-commit hooks (#12475)

2025-01-27 17:23:08 -07:00